jnulzl

you are right!

@mayankuxtc Maybe you can refer [my implement](https://github.com/jnulzl/PRNet)

@dfcv24 @zhangguanqun Hello,I want to load pretrained model in gpu mode and then predict a image by Predictor interface, but I cannot do it. do you make it????? Can you...

@eric612 OK,Have done！

@ElbertLi @AllenDun see[issues12](https://github.com/farmingyard/caffe-mobilenet/issues/12)

There is no parameter in SignedSqrt layer ,so there is nothing to add sin caffe.proto.

呵呵，其实我也没用过，就是感觉没有的话会缺少点东西，既然有这个参数说不定啥时候就会有人用了，还是多谢您了。

好的，我明白了，非常感谢您的高效、及时解惑！

@zoufangyu1987 @kunyao2015 实现步骤： 1、把模型转成caffemodel; 2、前后处理自己c++实现； 3、Done! 亲测可以，祝你好运！

@zoufangyu1987 不好意思，暂时不行